[RFC PATCH] Implement diskseq checks in blkback

[Demi Marie Obenour]

This allows specifying a disk sequence number in XenStore.  If it does
not match the disk sequence number of the underlying device, the device
will not be exported and a warning will be logged.  Userspace can use
this to eliminate race conditions due to major/minor number reuse.
Older kernels will ignore this, so it is safe for userspace to set it
unconditionally.

Signed-off-by: Demi Marie Obenour <demi@xxxxxxxxxxxxxxxxxxxxxx>
---
I'm marking this patch as RFC because I have not tested it beyond
compiliation, and because I want to get feedback on the API before I put
more effort into it.

 drivers/block/xen-blkback/xenbus.c | 35 ++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 97de13b14175eb8ced14d1649a3be461a464ee8a..cb531236b19709c791a82c868bfb4ed9aa284485 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -480,7 +480,7 @@ MODULE_PARM_DESC(feature_persistent,
 
 static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 			  unsigned major, unsigned minor, int readonly,
-			  int cdrom)
+			  bool cdrom, u64 diskseq)
 {
 	struct xen_vbd *vbd;
 	struct block_device *bdev;
@@ -508,6 +508,25 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 		xen_vbd_free(vbd);
 		return -ENOENT;
 	}
+
+	if (diskseq != (u64)-1) {
+		struct gendisk *disk = bdev->bd_disk;
+		if (unlikely(disk == NULL)) {
+			pr_err("xen_vbd_create: device %08x has no gendisk\n",
+			       vbd->pdevice);
+			xen_vbd_free(vbd);
+			return -EFAULT;
+		}
+
+		if (unlikely(disk->diskseq != diskseq)) {
+			pr_warn("xen_vbd_create: device %08x has incorrect sequence "
+				"number 0x%llx (expected 0x%llx)\n",
+				vbd->pdevice, disk->diskseq, diskseq);
+			xen_vbd_free(vbd);
+			return -ENODEV;
+		}
+	}
+
 	vbd->size = vbd_sz(vbd);
 
 	if (cdrom || disk_to_cdi(vbd->bdev->bd_disk))
@@ -712,6 +731,7 @@ static void backend_changed(struct xenbus_watch *watch,
 	int cdrom = 0;
 	unsigned long handle;
 	char *device_type;
+	unsigned long long diskseq;
 
 	pr_debug("%s %p %d\n", __func__, dev, dev->otherend_id);
 
@@ -730,6 +750,17 @@ static void backend_changed(struct xenbus_watch *watch,
 		return;
 	}
 
+	err = xenbus_scanf(XBT_NIL, dev->nodename, "diskseq", "%llx", &diskseq);
+	if (err == -ENOENT) {
+		diskseq = (uint64_t)-1;
+	} else if (err != 1) {
+		xenbus_dev_fatal(dev, err, "reading diskseq");
+		return;
+	} else if (diskseq == (uint64_t)-1) {
+		xenbus_dev_fatal(dev, err, "UINT64_MAX is not a valid diskseq");
+		return;
+	}
+
 	if (be->major | be->minor) {
 		if (be->major != major || be->minor != minor)
 			pr_warn("changing physical device (from %x:%x to %x:%x) not supported.\n",
@@ -763,7 +794,7 @@ static void backend_changed(struct xenbus_watch *watch,
 	be->minor = minor;
 
 	err = xen_vbd_create(be->blkif, handle, major, minor,
-			     !strchr(be->mode, 'w'), cdrom);
+			     !strchr(be->mode, 'w'), cdrom, diskseq);
 
 	if (err)
 		xenbus_dev_fatal(dev, err, "creating vbd structure");
-- 
Sincerely,
Demi Marie Obenour (she/her/hers)
Invisible Things Lab